Hao Sun

Hao Sun

Auto-generated profile, based on publicly available information

Hao Sun

Key Laboratory of Technology in Geo-spatial Information Processing and Application System, Institute of Electronics, Chinese Academy of Sciences, Beijing 100190, China

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
18 January 2018 in Remote Sensing
Verified
Journal Article
Open access
PDF file
XYXue Yang
Xue Yang
HSHao Sun
Hao Sun
KFKun Fu
Kun Fu
JYJirui Yang
Jirui Yang
XSXian Sun
Xian Sun
ZGZhi Guo
Zhi Guo
Ship detection has been playing a significant role in the field of remote sensing for a long time, but it is still full of challenges. The main limitations of traditional ship detection methods usually lie in the complexity of application scenarios, the difficulty of intensive object detection, and the redundancy of the detection region. In order to solve these problems above, we propose a framework called Rotation Dense Feature Pyramid Networks (R-DFPN) which can effectively detect ships in different scenes including ocean and port. Specifically, we put forward the Dense Feature Pyramid Network (DFPN), which is aimed at solving problems resulting from the narrow width of the ship. Compared with previous multiscale detectors such as Feature Pyramid Network (FPN), DFPN builds high-level semantic feature-maps for all scales by means of dense connections, through which feature propagation is enhanced and feature reuse is encouraged. Additionally, in the case of ship rotation and dense arrangement, we design a rotation anchor strategy to predict the minimum circumscribed rectangle of the object so as to reduce the redundant detection region and improve the recall. Furthermore, we also propose multiscale region of interest (ROI) Align for the purpose of maintaining the completeness of the semantic and spatial information. Experiments based on remote sensing images from Google Earth for ship detection show that our detection method based on R-DFPN representation has state-of-the-art performance.

6 December 2018 in Remote Sensing
Verified
Journal Article
Open access
PDF file
KFKun Fu
Kun Fu
WLWanxuan Lu
Wanxuan Lu
WDWenhui Diao
Wenhui Diao
MYMenglong Yan
Menglong Yan
HSHao Sun
Hao Sun
XSXian Sun
Xian Sun
Binary segmentation in remote sensing aims to obtain binary prediction mask classifying each pixel in the given image. Deep learning methods have shown outstanding performance in this task. These existing methods in fully supervised manner need massive high-quality datasets with manual pixel-level annotations. However, the annotations are generally expensive and sometimes unreliable. Recently, using only image-level annotations, weakly supervised methods have proven to be effective in natural imagery, which significantly reduce the dependence on manual fine labeling. In this paper, we review existing methods and propose a novel weakly supervised binary segmentation framework, which is capable of addressing the issue of class imbalance via a balanced binary training strategy. Besides, a weakly supervised feature-fusion network (WSF-Net) is introduced to adapt to the unique characteristics of objects in remote sensing image. The experiments were implemented on two challenging remote sensing datasets: Water dataset and Cloud dataset. Water dataset is acquired by Google Earth with a resolution of 0.5 m, and Cloud dataset is acquired by Gaofen-1 satellite with a resolution of 16 m. The results demonstrate that using only image-level annotations, our method can achieve comparable results to fully supervised methods.

6 February 2018 in Remote Sensing
Verified
Journal Article
Open access
PDF file
YLYang Li
Yang Li
KFKun Fu
Kun Fu
HSHao Sun
Hao Sun
XSXian Sun
Xian Sun
Aircraft detection has attracted increasing attention in the field of remote sensing image analysis. Complex background, illumination change and variations of aircraft kind and size in remote sensing images make the task challenging. In our work, we propose an effective aircraft detection framework based on reinforcement learning and a convolutional neural network (CNN) model. Aircraft in remote sensing images can be accurately and robustly located with the help of the searching mechanism that the candidate region is dynamically reduced to the correct location of aircraft, which is implemented through reinforcement learning. The detection framework overcomes the difficulties that the current detection methods based on reinforcement learning are only able to detect a fixed number of objects. Specifically, we adopt the restricted EdgeBoxes that generate the high-quality candidate boxes through the prior aircraft knowledge at first. Then, we train an intelligent detection agent through reinforcement learning and apprenticeship learning. The detection agent accurately locates the aircraft in the candidate boxes within several actions, and it even performs better than the greed strategy in apprenticeship learning. During the final detection step, we carefully design the CNN model that predicts the probability that the localization result generated by the detection agent is an aircraft. Comparative experiments demonstrate the accuracy and efficiency of our aircraft detection framework.

16 July 2018 in Remote Sensing
Verified
Journal Article
Open access
PDF file
YZYuhang Zhang
Yuhang Zhang
HSHao Sun
Hao Sun
JZJiawei Zuo
Jiawei Zuo
HWHongqi Wang
Hongqi Wang
GXGuangluan Xu
Guangluan Xu
XSXian Sun
Xian Sun
Aircraft type recognition plays an important role in remote sensing image interpretation. Traditional methods suffer from bad generalization performance, while deep learning methods require large amounts of data with type labels, which are quite expensive and time-consuming to obtain. To overcome the aforementioned problems, in this paper, we propose an aircraft type recognition framework based on conditional generative adversarial networks (GANs). First, we design a new method to precisely detect aircrafts’ keypoints, which are used to generate aircraft masks and locate the positions of the aircrafts. Second, a conditional GAN with a region of interest (ROI)-weighted loss function is trained on unlabeled aircraft images and their corresponding masks. Third, an ROI feature extraction method is carefully designed to extract multi-scale features from the GAN in the regions of aircrafts. After that, a linear support vector machine (SVM) classifier is adopted to classify each sample using their features. Benefiting from the GAN, we can learn features which are strong enough to represent aircrafts based on a large unlabeled dataset. Additionally, the ROI-weighted loss function and the ROI feature extraction method make the features more related to the aircrafts rather than the background, which improves the quality of features and increases the recognition accuracy significantly. Thorough experiments were conducted on a challenging dataset, and the results prove the effectiveness of the proposed aircraft type recognition framework.

30 November 2018 in Remote Sensing
Verified
Journal Article
Open access
PDF file
KFKun Fu
Kun Fu
YLYang Li
Yang Li
HSHao Sun
Hao Sun
XYXue Yang
Xue Yang
GXGuangluan Xu
Guangluan Xu
XSXian Sun
Xian Sun
Ship detection plays an important role in automatic remote sensing image interpretation. The scale difference, large aspect ratio of ship, complex remote sensing image background and ship dense parking scene make the detection task difficult. To handle the challenging problems above, we propose a ship rotation detection model based on a Feature Fusion Pyramid Network and deep reinforcement learning (FFPN-RL) in this paper. The detection network can efficiently generate the inclined rectangular box for ship. First, we propose the Feature Fusion Pyramid Network (FFPN) that strengthens the reuse of different scales features, and FFPN can extract the low level location and high level semantic information that has an important impact on multi-scale ship detection and precise location of dense parking ships. Second, in order to get accurate ship angle information, we apply deep reinforcement learning to the inclined ship detection task for the first time. In addition, we put forward prior policy guidance and a long-term training method to train an angle prediction agent constructed through a dueling structure Q network, which is able to iteratively and accurately obtain the ship angle. In addition, we design soft rotation non-maximum suppression to reduce the missed ship detection while suppressing the redundant detection boxes. We carry out detailed experiments on the remote sensing ship image dataset, and the experiments validate that our FFPN-RL ship detection model has efficient detection performance.

11 April 2025 in Proceedings of the AAAI Conference on Artificial Intelligence
Verified
Journal Article
Open access
PDF file
HHHaojian Huang
Haojian Huang
CQChuanyu Qin
Chuanyu Qin
ZLZhe Liu
Zhe Liu
KMKaijing Ma
Kaijing Ma
JCJin Chen
Jin Chen
ZHZhongjiang He
Zhongjiang He
Multi-view classification (MVC) faces inherent challenges due to domain gaps and inconsistencies across different views, often resulting in uncertainties during the fusion process. While Evidential Deep Learning (EDL) has been effective in addressing view uncertainty, existing methods predominantly rely on the Dempster-Shafer combination rule, which is sensitive to conflicting evidence and often neglects the critical role of neighborhood structures within multi-view data. To address these limitations, we propose a Trusted Unified Feature-NEighborhood Dynamics (TUNED) model for robust MVC. This method effectively integrates local and global feature-neighborhood (F-N) structures for robust decision-making. Specifically, we begin by extracting local F-N structures within each view. To further mitigate potential uncertainties and conflicts in multi-view fusion, we employ a selective Markov random field that adaptively manages cross-view neighborhood dependencies. Additionally, we employ a shared parameterized evidence extractor that learns global consensus conditioned on local F-N structures, thereby enhancing the global integration of multi-view features. Experiments on benchmark datasets show that our method improves accuracy and robustness over existing approaches, particularly in scenarios with high uncertainty and conflicting views.